Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0671. Min Range: -4.0671
Max Act: 4.0671. Min Act: -0.1700
Data Index: 1716276 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0671. Min Range: -4.0671
Max Act: 4.0671. Min Act: -0.1700
Data Index: 8663890 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0671. Min Range: -4.0671
Max Act: 4.0671. Min Act: -0.1700
Data Index: 796166 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0671. Min Range: -4.0671
Max Act: 4.0046. Min Act: -0.1700
Data Index: 7503583 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.9421. Min Act: -0.1700
Data Index: 5698700 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.9108. Min Act: -0.1700
Data Index: 4272762 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.8795. Min Act: -0.1700
Data Index: 7756467 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.8795. Min Act: -0.1700
Data Index: 5327958 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.8483. Min Act: -0.1700
Data Index: 4557194 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.8483. Min Act: -0.1700
Data Index: 8796593 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.8170. Min Act: -0.1700
Data Index: 2469330 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.8170. Min Act: -0.1700
Data Index: 3039849 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.8170. Min Act: -0.1700
Data Index: 2649395 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.7544. Min Act: -0.1700
Data Index: 1037397 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.7857. Min Act: -0.1700
Data Index: 796165 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.7857. Min Act: -0.1700
Data Index: 8164930 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.7544. Min Act: -0.1700
Data Index: 1729841 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.7544. Min Act: -0.1700
Data Index: 410138 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.7544. Min Act: -0.1700
Data Index: 5906546 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0671. Min Range: -4.0671
Max Act: 3.7544. Min Act: -0.1700
Data Index: 3273210 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19